High Performance FFT on SGI Altix 3700

We have developed a high-performance FFT on SGI Altix 3700, improving the efficiency of the floating-point operations required to compute FFT by using a kind of loop fusion technique. As a result, we achieved a performance of 4.94 Gflops at 1-D FFT of length 4096 with

• Type: Conference
• Year: 2007
• Where: HPCC
• Authors: Akira Nukada, Daisuke Takahashi, Reiji Suda, Akira Nishida
• Keywords: 1-d Fft, Distributed And Parallel Computing, HPCC 2007, Loop Fusion Technique, SGI Altix